In the formation of extended noun phrases, expressions are used that describe some dimension. Weight is described by each of the prenominal expressions in heavy rock, too much ballast, 2 lb rock, 2 lbs of rocks. The central claim of this paper is that the position of these types of expressions within the noun phrase limits the kinds of dimensions they may describe. The limitations have to do wi...

We report on experiments in reference resolution using a decision tree approach. We started with a standard feature set used in previous work, which led to moderate results. A closer examination of the performance of the features for different forms of anaphoric expressions showed good results for pronouns, moderate results for proper names, and poor results for definite noun phrases. We then i...

This paper sets forth the argument for revisiting fixed phrases in the light of the knowledge that their fixedness is not necessarily something to be taken for granted. It focuses on the location and analysis of variant forms in general reference corpora. Existing phraseological structures, including collocational frameworks, idiom schemas and semi-prepackaged phrases, are introduced by way of ...

In a broad range of natural language processing tasks, large-scale knowledge-base of paraphrases is anticipated to improve their performance. The key issue in creating such a resource is to establish a practical method of computing semantic equivalence and syntactic substitutability, i.e., paraphrasability, between given pair of expressions. This paper addresses the issues of computing paraphra...

A sample of 56 general practitioners were asked to rate, on a percentage scale, 23 words or phrases which denote frequency or likelihood. The hypothetical context of the exercise was that of communicating to patients the probability of a side-effect (headache) arising from an unspecified prescription medicine. Median phrase ratings ranged from 'never' at 0% to 'certain' at 95% with a 50% rating...

To test predictions of a forward modeling framework for spoken language processing, we characterized effects of context speech rate on the real-time interpretation of indefinite noun phrases using the visual world paradigm. The speech rate of sentence material distal to the onset of the noun phrase was manipulated such that the segments surrounding the determiner a in singular noun phrases had ...

We propose a method of extracting cause information from Japanese newspaper articles concerning business performance. Cause information is useful for investors in selecting companies to invest. Our method extracts cause information as a form of causal expression by using statistical information and initial clue phrases automatically. Our method can extract causal expressions without predetermin...

Abstract This paper explores the rich diversity in structural possibilities that are available for (simple) nominal expressions Australian languages. First, I identify a number of construction types found across 50 language sample, which may be recognised by using restricted set parameters. show an important factor is whether given parameter (such as word order) generalised or displayed only so...

In this talk, I discuss the ability of compositional distributional semantics to model adjective modification. I present three studies that explore the degree to which semantic intuitions are grounded in the distributional representations of adjective-noun phrases, as well as provide insight into various linguistic phenomena by extracting unsupervised cues from these distributional representati...